How to use PyTorch for deep learning on CentOS

Using PyTorch for deep learning on CentOS, you can follow these steps:

1. Install Anaconda3

First, you need to install the Anaconda3 environment on CentOS. You can download the installation package suitable for CentOS from the official website of Anaconda and follow the installation wizard to install it.

 wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
bash Miniconda3-latest-Linux-x86_64.sh

2. Create and activate the virtual environment

Create a new virtual environment and activate it. For example, create a virtual environment called pytorch and install Python version 3.8.

 conda create -n pytorch python=3.8
conda activated pytorch

3. Install PyTorch

In an activated environment, use conda to install PyTorch. Select the appropriate installation command based on whether GPU support is required. If GPU support is required, CUDA and cuDNN need to be installed.

Install CPU-enabled PyTorch

 conda install pytorch torchvision torchaudio cpuonly -c pytorch

Install GPU-enabled PyTorch

 conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch -c conda-forge

Note: The version number of cudatoolkit may need to be adjusted according to your CUDA version. You can view available CUDA versions by running conda info cudatoolkit.

4. Verify the installation

After the installation is completed, you can verify that PyTorch is installed successfully. Run the following Python code:

 import torch
print(torch.__version__)
print(torch.cuda.is_available())

If everything works fine, you should be able to see the version number of PyTorch and whether CUDA is available (depending on your system configuration).

5. Carry out deep learning projects

Once PyTorch is installed successfully, you can start working on a deep learning project. Here is a simple example showing how to define and train a neural network using PyTorch:

Defining neural networks

 import torch
import torch.nn as nn
import torch.optim as optim

class SimpleNN(nn.Module):
    def __init__(self):
        super(SimpleNN, self).__init__()
        self.fc1 = nn.Linear(784, 128)
        self.fc2 = nn.Linear(128, 64)
        self.fc3 = nn.Linear(64, 10)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        Return x

model = SimpleNN()

Prepare data

 from torchvision import datasets, transforms

transform = transforms.Compose([transforms.ToTensor()])

train_dataset = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
test_dataset = datasets.MNIST(root='./data', train=False, download=True, transform=transform)

train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=64, shuffle=False)

Training the model

 criteria = nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01)

for epoch in range(5):
    for data, target in train_loader:
        optimizer.zero_grad()
        output = model(data)
        loss = criteria(output, target)
        loss.backward()
        optimizer.step()

Through the above steps, you can successfully install PyTorch on CentOS and start a deep learning project. If you encounter problems during the installation process, it is recommended to consult the official PyTorch documentation or seek community help.

The above is the detailed content of How to use PyTorch for deep learning on CentOS. For more information, please follow other related articles on the PHP Chinese website!